Research map / 3D vision / Human pose estimation
DogMo: A Large-Scale Multi-View RGB-D Dataset for 4D Canine Motion Recovery
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add stage 1 coarse alignment (ablation) | three-stage SMAL fitting · DogMo single-view RGB-D | F-score: 0.6619 -> 0.7673 | Improved |
| add stage 1 coarse alignment (ablation) | three-stage SMAL fitting · DogMo single-view RGB | IoU: 0.6024 -> 0.6505 | Improved |
| add stage 1 coarse alignment (ablation) | three-stage SMAL fitting · DogMo multi-view RGB | F-score: 0.9096 -> 0.9107 | No clear effect |
| add stage 3 temporal refinement (ablation) | three-stage SMAL fitting · DogMo single-view RGB | Jitter: 0.0211 -> 0.0206 | Improved |
| add stage 3 temporal refinement (ablation) | three-stage SMAL fitting · DogMo single-view RGB | IoU: 0.6491 -> 0.6505 | No clear effect |
| add stage 3 temporal refinement (ablation) | three-stage SMAL fitting · DogMo multi-view RGB | IoU: 0.6271 -> 0.6258 | No clear effect |
| replace stage-3 smoothness with Kalman smoothing (ablation) | stage 3 · DogMo single-view RGB (temporal smoothing alternatives) | IoU: 0.6505 -> 0.6251 | Hurt |
| replace stage-3 smoothness with spline smoothing (ablation) | stage 3 · DogMo single-view RGB (temporal smoothing alternatives) | IoU: 0.6505 -> 0.4821 | Hurt |
| use depth input (RGB-D) instead of RGB | three-stage SMAL fitting · DogMo single-view RGB | F-score: 0.3593 -> 0.7673 | Improved |
| use multi-view input instead of single-view RGB | three-stage SMAL fitting · DogMo single-view RGB | F-score: 0.3593 -> 0.9107 | Improved |
| use the proposed pipeline instead of AnimalAvatar | three-stage SMAL fitting · DogMo single-view RGB | F-score: 0.0283 -> 0.3593 | Improved |
| use the proposed pipeline instead of AnimalAvatar | three-stage SMAL fitting · DogMo single-view RGB | optimization time (min): 114.68 -> 18.78 | Improved |
Closest papers by meaning
- RGBD-Dog: Predicting Canine Pose from RGBD Sensors (CVPR 2020 · similarity 0.90)
- Who Left the Dogs Out? 3D Animal Reconstruction with Expectation Maximization in the Loop (ECCV 2020 · similarity 0.88)
- Web-Scale Collection of Video Data for 4D Animal Reconstruction (NeurIPS 2025 · similarity 0.87)
- BEAST3D: animal behavioral analysis and neural encoding from multi-view video via Gaussian splatting (NeurIPS 2026 · similarity 0.87)
- SAM 3D Animal: Promptable Animal 3D Reconstruction from Images in the Wild (NeurIPS 2026 · similarity 0.85)
- Animal-Bench: Benchmarking Multimodal Video Models for Animal-centric Video Understanding (NeurIPS 2024 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
